claude-handoff
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious instructions, obfuscation, or unauthorized access patterns were detected.
- [DATA_EXFILTRATION]: The skill contains specific instructions for the agent to redact sensitive information before passing data to a new background agent.
- [COMMAND_EXECUTION]: The skill utilizes the
claudeCLI for its intended purpose of agent lifecycle management. - [PROMPT_INJECTION]: The skill ingests conversation data to seed new sessions; this is a standard operational surface for handoff skills and no bypass attempts were found.
Audit Metadata